INDEX

Explanations

references to "ide" or "ideological" terms

oai_token-act-pair · gpt-3.5-turbo

terms related to ideologies

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enegger

-0.98

iona

-0.92

ichick

-0.87

ufact

-0.76

é¾

-0.71

thening

-0.71

wagen

-0.71

cffff

-0.69

itton

-0.69

lishing

-0.68

POSITIVE LOGITS

gger

0.97

maid

0.90

ously

0.88

lli

0.88

ll

0.86

lla

0.79

llo

0.78

creen

0.76

hare

0.73

 Dhabi

0.72

Activations Density 0.031%

references to "ide" or "ideological" terms

terms related to ideologies

No Comments

No Known Activations